© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 23203
    Prev
    Next
    INDEX
    Explanations

    words related to visual attention or focus, like "gaze," "stare," or "gazing."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to focused attention and visual engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sol
    -0.77
    MER
    -0.75
    cel
    -0.74
    nic
    -0.72
    surv
    -0.72
    balanced
    -0.69
    solid
    -0.69
    cy
    -0.68
    vacc
    -0.67
    official
    -0.66
    POSITIVE LOGITS
     gaze
    1.37
     gazing
    1.01
     stare
    0.84
     stares
    0.80
     attent
    0.79
     cursor
    0.77
     wink
    0.74
     gazed
    0.74
     nodd
    0.72
    enance
    0.70
    Activations Density 0.003%

    No Known Activations